MILESTONE: Complete 5ARIP10 project

.gitignore

@@ -61,17 +61,13 @@ venv.bak/
 
 # Data
 /data
-/data081
-/SAM-Med3D
-/models
-*.pth
+/assets
 
 #WandB
 /notebooks/wandb
 /src/wandb
 /wandb
 
 # Medical files
-*.dcm
 *.nii
 *.nii.gz

notebooks/evaluate.ipynb → Deprecated-notebooks/evaluate.ipynb

@@ -164,6 +164,31 @@
     "new_image = nib.Nifti1Image(seg_numpy, np.eye(4))\n",
     "nib.save(new_image, \"target.nii\")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([1, 512, 512, 133])"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from diffdrr.data import load_example_ct\n",
+    "\n",
+    "# Load the example CT data\n",
+    "subject = load_example_ct()\n",
+    "\n",
+    "subject.volume.data.shape"
+   ]
   }
  ],
  "metadata": {

README.md

@@ -1,21 +1,33 @@
-# 5ARIP10 Interdisciplinary team project
+# 5ARIP10 Interdisciplinary Team Project Track 3 Group 3
 
 ## Introduction
-This project, conducted in collaboration between Eindhoven University of Technology (TU/e) and Philips, is focused on .......... for the Image Guided Therapy Challenge on Transarterial Chemoembolization (TACE) procedures. The goal of this project ..........
+
+This project, conducted in collaboration between Eindhoven University of Technology (TU/e) and Philips, is focused on developing an AI solution for the Image Guided Therapy Challenge on Transarterial Chemoembolization (TACE) procedures. The goal of this project is to enhance the efficiency and accuracy of TACE procedures using advanced AI techniques.
 
 ## Getting Started
 
 ### Prerequisites
 
-List what software and libraries you need to install the software and how to install them.
+This project is developed using Python and pip for package management. Ensure you have the following installed on your system:
+
+- Python 3.7 or higher
 
 ### Installation
 
-Provide step by step series of examples that tell you how to get a development environment running.
+To set up a development environment for this project, follow these steps:
+
+1. Clone the repository to your local machine: `git clone https://github.com/LucianoDeben/5ARIP10-ITP-T3G3.git`
+2. Navigate to the project directory.
+3. Create a virtual environment: `python -m venv env` or `conda create --name env`.
+4. Activate the virtual environment: `source env/bin/activate` (Linux/macOS) or `.\env\Scripts\activate` (Windows) or `conda activate myenv` (Conda).
+5. Install the required packages: `pip install -r requirements.txt`
 
-## Usage
+### Usage
 
-Explain how to use your project. Provide examples.
+After setting up the project, you can run the Streamlit demo application in `src`:
+
+1. `cd src`
+2. `streamlit run app.py`
 
 ## License
 
@@ -30,8 +42,9 @@ We would like to thank the following resources and individuals:
 - Gopalakrishnan, Vivek, and Golland, Polina for their work on [fast auto-differentiable digitally reconstructed radiographs](https://link.springer.com/chapter/10.1007/978-3-031-23179-7_1). We utilized their [`DiffDRR`](https://github.com/eigenvivek/DiffDRR?tab=readme-ov-file#user-content-fn-1-aa759ff9097582506ce05933e125ab0a): Auto-differentiable DRR rendering and optimization in PyTorch in our project.
 
 ## Authors
+
 This project was developed by:
 
-- Author 1: Crapels, Dhani - [email protected]
-- Author 2: Deben, Luciano - [email protected]
-- Author 3: Bierenbroodspot, Sven - [email protected]
+- Crapels, Dhani - <[email protected]>
+- Deben, Luciano - <[email protected]>
+- Bierenbroodspot, Sven - <[email protected]>